{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:52USBR36WNGA43UYHKK4KFZMZL","short_pith_number":"pith:52USBR36","schema_version":"1.0","canonical_sha256":"eea920c77eb34c0e6e983a95c5172ccad08d2eed9a9ed6df64456f174f4ce0b1","source":{"kind":"arxiv","id":"1709.02327","version":1},"attestation_state":"computed","paper":{"title":"Feature selection in high-dimensional dataset using MapReduce","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.DC","authors_text":"Claudio Reggiani, Gianluca Bontempi, Yann-A\\\"el Le Borgne","submitted_at":"2017-09-07T16:05:51Z","abstract_excerpt":"This paper describes a distributed MapReduce implementation of the minimum Redundancy Maximum Relevance algorithm, a popular feature selection method in bioinformatics and network inference problems. The proposed approach handles both tall/narrow and wide/short datasets. We further provide an open source implementation based on Hadoop/Spark, and illustrate its scalability on datasets involving millions of observations or features."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1709.02327","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2017-09-07T16:05:51Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"505aee52dbe1f6b94dbfd21ecf4ceb8bc3b3047761ca34ad62c0b099a533fa25","abstract_canon_sha256":"4f6d8fc659c79789fe7ea6765b0da5dcc85929fc55c131bc9f92c94808b50d07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:49.461106Z","signature_b64":"u+gp9Sf0uzJZ/uPe/KbKBY6Zsmss0noanGSuiroFknn15NHEAGdlpYZFPAMg7acAoLihaZzHqU7vVXUFUffFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eea920c77eb34c0e6e983a95c5172ccad08d2eed9a9ed6df64456f174f4ce0b1","last_reissued_at":"2026-05-18T00:35:49.460384Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:49.460384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature selection in high-dimensional dataset using MapReduce","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.DC","authors_text":"Claudio Reggiani, Gianluca Bontempi, Yann-A\\\"el Le Borgne","submitted_at":"2017-09-07T16:05:51Z","abstract_excerpt":"This paper describes a distributed MapReduce implementation of the minimum Redundancy Maximum Relevance algorithm, a popular feature selection method in bioinformatics and network inference problems. The proposed approach handles both tall/narrow and wide/short datasets. We further provide an open source implementation based on Hadoop/Spark, and illustrate its scalability on datasets involving millions of observations or features."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.02327","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1709.02327","created_at":"2026-05-18T00:35:49.460497+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.02327v1","created_at":"2026-05-18T00:35:49.460497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.02327","created_at":"2026-05-18T00:35:49.460497+00:00"},{"alias_kind":"pith_short_12","alias_value":"52USBR36WNGA","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"52USBR36WNGA43UY","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"52USBR36","created_at":"2026-05-18T12:31:00.734936+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/52USBR36WNGA43UYHKK4KFZMZL","json":"https://pith.science/pith/52USBR36WNGA43UYHKK4KFZMZL.json","graph_json":"https://pith.science/api/pith-number/52USBR36WNGA43UYHKK4KFZMZL/graph.json","events_json":"https://pith.science/api/pith-number/52USBR36WNGA43UYHKK4KFZMZL/events.json","paper":"https://pith.science/paper/52USBR36"},"agent_actions":{"view_html":"https://pith.science/pith/52USBR36WNGA43UYHKK4KFZMZL","download_json":"https://pith.science/pith/52USBR36WNGA43UYHKK4KFZMZL.json","view_paper":"https://pith.science/paper/52USBR36","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.02327&json=true","fetch_graph":"https://pith.science/api/pith-number/52USBR36WNGA43UYHKK4KFZMZL/graph.json","fetch_events":"https://pith.science/api/pith-number/52USBR36WNGA43UYHKK4KFZMZL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/52USBR36WNGA43UYHKK4KFZMZL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/52USBR36WNGA43UYHKK4KFZMZL/action/storage_attestation","attest_author":"https://pith.science/pith/52USBR36WNGA43UYHKK4KFZMZL/action/author_attestation","sign_citation":"https://pith.science/pith/52USBR36WNGA43UYHKK4KFZMZL/action/citation_signature","submit_replication":"https://pith.science/pith/52USBR36WNGA43UYHKK4KFZMZL/action/replication_record"}},"created_at":"2026-05-18T00:35:49.460497+00:00","updated_at":"2026-05-18T00:35:49.460497+00:00"}